How to Use the Kavkom MCP in Mastra AI

Q: How do I initialize the Kavkom MCP Server in Mastra AI?

Instantiate new MCPClient and pass your Vinkius URL in the servers object. Then call mcpClient.listTools() and spread the results into your agent definition.

Q: Can I require human approval before sending Kavkom texts?

Absolutely. You set requireToolApproval on the specific SMS tool. The workflow will halt until an authorized user signs off on the action.

Build reliable telephony workflows in Mastra AI using this Kavkom MCP Server connection.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kavkom MCP to Mastra AI

Create your Vinkius account to connect Kavkom to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Kavkom with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fetch phone records with built-in retries

`list_calls` and `get_call_details` fetch phone logs for your automated workflows. Mastra AI takes these tools and wraps them in its native retry logic. If the API drops a connection during a massive data pull, the workflow doesn't crash. It just waits and tries again using exponential backoff. You spend zero time writing custom error handling for network blips. The engine manages the state, ensuring your call data always makes it to the next step in your pipeline.

Execute conditional SMS logic

`send_sms_message` and `list_sms_history` push text messages out to your customers. You can build conditional branches based on the results. If a text fails to send, Mastra routes the logic to an email fallback or alerts an admin. You might want a human to look at outgoing texts before they hit a customer's phone. Mastra supports `requireToolApproval` out of the box. The workflow pauses, waits for a manager to click approve, and then executes the send tool.

Map staff to external leads

`list_team_members` and `create_contact` map your internal staff to incoming prospects. This MCP Server exposes your entire account directory. You can build logic that assigns a newly created contact to the specific sales rep who handled their last call. Deployment takes one command. You initialize the connection with `new MCPClient`, spread the tools into your agent, and push to your cloud provider. Mastra auto-detects the transport layer automatically.

Setup guide

Set up Kavkom MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Kavkom tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "kavkom-mcp-client",
  servers: {
    "kavkom-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Kavkom Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Kavkom tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Kavkom transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Kavkom. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Kavkom now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Kavkom MCP in Mastra AI

Instantiate `new MCPClient` and pass your Vinkius URL in the servers object. Then call `mcpClient.listTools()` and spread the results into your agent definition.

Yes. The built-in workflow engine handles failures gracefully. You can configure exponential backoff rules for `send_sms_message`.

No. The framework parses the tool definitions automatically. It reads the schemas and makes them available to your workflows immediately.

Absolutely. You set `requireToolApproval` on the specific SMS tool. The workflow will halt until an authorized user signs off on the action.

The platform relies on ephemeral execution environments. Text message data passes through the isolated memory space and vanishes once the response ships back to your client.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript